Important: Isaac Sim support
Note: For Isaac Sim support, the community is gradually transitioning from this forum to the Isaac Sim GitHub repository so that questions and issues can be tracked, searched, and resolved more efficiently in one place. Whenever possible, please create a GitHub Discussion or Issue there instead of starting a new forum topic.
Note: For any Isaac Lab topics, please submit your topic to its GitHub repo ( GitHub - isaac-sim/IsaacLab: Unified framework for robot learning built on NVIDIA Isaac Sim · GitHub ) following the instructions provided on Isaac Lab’s Contributing Guidelines ( Contribution Guidelines — Isaac Lab Documentation ).
Please provide all relevant details below before submitting your post. This will help the community provide more accurate and timely assistance. After submitting, you can check the appropriate boxes. Remember, you can always edit your post later to include additional information if needed.
6.0.0
5.1.0
5.0.0
4.5.0
4.2.0
4.1.0
4.0.0
4.5.0
2023.1.1
2023.1.0-hotfix.1
Other (please specify):
Operating System
Ubuntu 24.04
Ubuntu 22.04
Ubuntu 20.04
Windows 11
Windows 10
Other (please specify):
GPU Information
- Model: RTX PRO 6000
- Driver Version: 580.82.09
Topic Description
Detailed Description
I have installed NVIDIA Isaac Sim 4.5 and configured IsaacLab correctly. When I try to run the official test scripts from IsaacLab, the GUI window crashes/quits immediately, and the program throws a runtime error.
This issue happens with both commands below:
-
python scripts/reinforcement_learning/rsl_rl/train.py --task=Isaac-Ant-v0 -
python scripts/demos/h1_locomotion.py
I would like to figure out the root cause of this issue: why does the GUI crash when running IsaacLab test cases?Meanwhile, I would like to ask whether upgrading to Isaac Sim 5.0 can resolve this compatibility and runtime error.
Error Messages
([INFO][AppLauncher]: Using device: cuda:0
[INFO][AppLauncher]: Loading experience file: /IsaacLab-main/apps/isaacsim_4_5/isaaclab.python.kit
Loading user config located at: ‘/isaacsim/kit/data/Kit/Isaac-Sim/4.5/user.config.json’
[Info] [carb] Logging to file: /isaacsim/kit/logs/Kit/Isaac-Sim/4.5/kit_20260512_175953.log
2026-05-12 09:59:53 [0ms] [Warning] [omni.kit.app.plugin] No crash reporter present, dumps uploading isn’t available.
2026-05-12 09:59:54 [945ms] [Warning] [carb.cudainterop.plugin] CUDA_VISIBLE_DEVICES environment variable is set.
2026-05-12 09:59:54 [945ms] [Warning] [carb.cudainterop.plugin] Note CUDA device enumeration and Omniverse device enumeration are different.
2026-05-12 09:59:54 [945ms] [Warning] [carb.cudainterop.plugin] Setting CUDA_VISIBLE_DEVICES can lead to undesired behavior or crashes.
2026-05-12 09:59:54 [1,193ms] [Warning] [gpu.foundation.plugin] Skipping NVIDIA GPU due CUDA being in bad state: NVIDIA RTX PRO 6000 Blackwell Server Edition
2026-05-12 09:59:54 [1,193ms] [Warning] [gpu.foundation.plugin] Please restart your system if CUDA is known to work in your system.
|---------------------------------------------------------------------------------------------|
| Driver Version: 580.82.09 | Graphics API: Vulkan
|=============================================================================================|
| GPU | Name | Active | LDA | GPU Memory | Vendor-ID | LUID |
| 0 | NVIDIA RTX PRO 6000 Blackwell .. | Yes: 0 | | 97887 MB | 10de | 0 |
| 1 | NVIDIA RTX PRO 6000 Blackwell .. | | | 97887 MB | 10de | 0 |
|=============================================================================================|
| OS: 20.04.6 LTS (Focal Fossa) ubuntu, Version: 20.04.6, Kernel: 5.15.0-139-generic
| Processor: Intel(R) Xeon(R) Platinum 8488C
| Cores: 96 | Logical Cores: 192
| Total Memory (MB): 257546 | Free Memory: 31245
|---------------------------------------------------------------------------------------------|
2026-05-12 09:59:55 [1,667ms] [Warning] [gpu.foundation.plugin] ECC is enabled on physical device 0
2026-05-12 09:59:57 [3,762ms] [Warning] [omni.isaac.dynamic_control] omni.isaac.dynamic_control is deprecated as of Isaac Sim 4.5. No action is needed from end-users.
2026-05-12 09:59:59 [6,195ms] [Warning] [omni.replicator.core.scripts.extension] No material configuration file, adding configuration to material settings directly.
2026-05-12 10:00:03 [9,299ms] [Warning] [rtx.neuraylib.plugin] [IRAY:RENDER] 1.1 IRAY rend warn : GPU with CUDA compute capability 12.0 is unsupported by this version of iray photoreal.
2026-05-12 10:00:03 [9,307ms] [Warning] [rtx.scenedb.plugin] SceneDbContext : TLAS limit buffer size warning
2026-05-12 10:00:04 [10,261ms] [Warning] [omni.usd-abi.plugin] No setting was found for ‘/rtx-defaults-transient/meshlights/forceDisable’
[16.962s] Simulation App Startup Complete
[INFO]: Parsing configuration from: isaaclab_tasks.manager_based.locomotion.velocity.config.h1.agents.rsl_rl_ppo_cfg:H1RoughPPORunnerCfg
Using pre-fetched pre-trained checkpoint
2026-05-12 10:00:11 [17,882ms] [Warning] [isaaclab.envs.manager_based_env] Seed not set for the environment. The environment creation may not be deterministic.
[INFO]: Base environment:
Environment device : cuda:0
Physics step-size : 0.005
Rendering step-size : 0.02
Environment step-size : 0.02
[INFO] Generating terrains randomly took : 0.247561 seconds
[INFO]: Time taken for scene creation : 2.592075 seconds
[INFO]: Starting the simulation. This may take a few seconds. Please wait…
18:00:15 [articulation.py] WARNING: Spatial tendons are not supported in Isaac Sim < 5.0: patching spatial-tendon getter and setter to use dummy value
[INFO]: Time taken for simulation start : 5.107742 seconds
Traceback (most recent call last):
File “/IsaacLab-main/scripts/demos/h1_locomotion.py”, line 226, in
main()
File “/IsaacLab-main/scripts/demos/h1_locomotion.py”, line 213, in main
demo_h1 = H1RoughDemo()
File “/IsaacLab-main/scripts/demos/h1_locomotion.py”, line 96, in _init_
self.env = RslRlVecEnvWrapper(ManagerBasedRLEnv(cfg=env_cfg))
File “/IsaacLab-main/source/isaaclab/isaaclab/envs/manager_based_rl_env.py”, line 80, in _init_
super()._init_(cfg=cfg)
File “/IsaacLab-main/source/isaaclab/isaaclab/envs/manager_based_env.py”, line 180, in _init_
self.load_managers()
File “/IsaacLab-main/source/isaaclab/isaaclab/envs/manager_based_rl_env.py”, line 117, in load_managers
super().load_managers()
File “/IsaacLab-main/source/isaaclab/isaaclab/envs/manager_based_env.py”, line 320, in load_managers
self.observation_manager = ObservationManager(self.cfg.observations, self)
File “/IsaacLab-main/source/isaaclab/isaaclab/managers/observation_manager.py”, line 83, in _init_
super()._init_(cfg, env)
File “//IsaacLab-main/source/isaaclab/isaaclab/managers/manager_base.py”, line 177, in _init_
self._prepare_terms()
File “IsaacLab-main/source/isaaclab/isaaclab/managers/observation_manager.py”, line 558, in _prepare_terms
obs_dims = tuple(term_cfg.func(self._env, **term_cfg.params).shape)
File “/IsaacLab-main/source/isaaclab/isaaclab/envs/utils/io_descriptors.py”, line 216, in wrapper
out = func(env, *args, **kwargs)
File “/IsaacLab-main/source/isaaclab/isaaclab/envs/mdp/observations.py”, line 68, in base_ang_vel
return asset.data.root_ang_vel_b
File “/IsaacLab-main/source/isaaclab/isaaclab/assets/articulation/articulation_data.py”, line 1048, in root_ang_vel_b
return self.root_com_ang_vel_b
File “/IsaacLab-main/source/isaaclab/isaaclab/assets/articulation/articulation_data.py”, line 837, in root_com_ang_vel_b
return math_utils.quat_apply_inverse(self.root_link_quat_w, self.root_com_ang_vel_w)
RuntimeError: nvrtc: error: invalid value for --gpu-architecture (-arch)
nvrtc compilation failed:
define NAN __int_as_float(0x7fffffff)
define POS_INFINITY __int_as_float(0x7f800000)
define NEG_INFINITY __int_as_float(0xff800000)
template
_device_ T maximum(T a, T b) {
return isnan(a) ? a : (a > b ? a : b);
}
template
_device_ T minimum(T a, T b) {
return isnan(a) ? a : (a < b ? a : b);
}
extern “C” _global_
void fused_mul_sub_add(float* tv_, float* tvec_7, float* tv__, float* tt_1, float* aten_add) {
{
if ((long long)(threadIdx.x) + 512ll * (long long)(blockIdx.x)<75ll ? 1 : 0) {
float v = __ldg(tvec_7 + ((long long)(threadIdx.x) + 512ll * (long long)(blockIdx.x)) % 3ll + 2ll * ((((long long)(threadIdx.x) + 512ll * (long long)(blockIdx.x)) / 3ll) * 3ll));
float v_1 = _ldg(tv_ + 7ll * (((long long)(threadIdx.x) + 512ll * (long long)(blockIdx.x)) / 3ll));
float v_2 = __ldg(tt_1 + (long long)(threadIdx.x) + 512ll * (long long)(blockIdx.x));
float v_3 = __ldg(tv_ + (long long)(threadIdx.x) + 512ll * (long long)(blockIdx.x));
aten_add[(long long)(threadIdx.x) + 512ll * (long long)(blockIdx.x)] = (v - v_1 * v_2) + v_3;
}}
})